Chroma

ChromaVectorStore

Bases: BaseVectorStore

Chroma is the AI-native open-source vector database. Embeddings are stored within a ChromaDB collection.

Attributes:

Name	Type	Description
embed_model	BaseEmbedding	Embedding model used to compute vectors.
collection_name	str	Name of the ChromaDB collection.
distance_strategy	str	Distance strategy for similarity search. Currently supports "cosine", "ip", and "l2". Defaults to cosine.

Example

from beekeeper.embeddings.huggingface import HuggingFaceEmbedding
from beekeeper.vector_stores.chroma import ChromaVectorStore

embedding = HuggingFaceEmbedding()
vector_db = ChromaVectorStore(embed_model=embedding)

model_post_init

model_post_init(__context)

Initialize ChromaDB client and collection after Pydantic validation.

add_documents

add_documents(documents: list[Document]) -> list

Add documents to the ChromaDB collection.

Parameters:

Name	Type	Description	Default
documents	list[Document]	List of documents to add to the collection.	required

query_documents

query_documents(query: str, top_k: int = 4) -> list[DocumentWithScore]

Performs a similarity search for the top-k most similar documents.

Parameters:

Name	Type	Description	Default
query	str	Query text.	required
top_k	int	Number of top results to return. Defaults to 4.	4

Returns:

Type	Description
list[DocumentWithScore]	list[DocumentWithScore]: List of the most similar documents.

delete_documents

delete_documents(ids: list[str]) -> None

Delete documents from the ChromaDB collection.

Parameters:

Name	Type	Description	Default
ids	list[str]	List of Document IDs to delete. Defaults to None.	required

get_all_documents

get_all_documents(include_fields: list[str] | None = None) -> list[Document]

Get all documents from vector store.